CN102150156B - 优化用于机器翻译的参数 - Google Patents

优化用于机器翻译的参数 Download PDF

Info

Publication number
CN102150156B
CN102150156B CN200980133134.8A CN200980133134A CN102150156B CN 102150156 B CN102150156 B CN 102150156B CN 200980133134 A CN200980133134 A CN 200980133134A CN 102150156 B CN102150156 B CN 102150156B
Authority
CN
China
Prior art keywords
translation
battle array
decoding
hypothesis
prime
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CN200980133134.8A
Other languages
English (en)
Chinese (zh)
Other versions
CN102150156A (zh
Inventor
沃尔夫冈·马赫赖
尚卡尔·库马尔
罗伊·W·特朗布利
弗朗茨·约瑟夫·欧池
伊格纳西奥·E·塞耶
雅各布·乌兹科瑞特
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Google LLC
Original Assignee
Google LLC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Google LLC filed Critical Google LLC
Publication of CN102150156A publication Critical patent/CN102150156A/zh
Application granted granted Critical
Publication of CN102150156B publication Critical patent/CN102150156B/zh
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/42—Data-driven translation
    • G06F40/44—Statistical methods, e.g. probability models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Algebra (AREA)
  • Pure & Applied Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Machine Translation (AREA)
CN200980133134.8A 2008-07-03 2009-07-02 优化用于机器翻译的参数 Expired - Fee Related CN102150156B (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US7826208P 2008-07-03 2008-07-03
US61/078,262 2008-07-03
PCT/US2009/049613 WO2010003117A2 (en) 2008-07-03 2009-07-02 Optimizing parameters for machine translation

Publications (2)

Publication Number Publication Date
CN102150156A CN102150156A (zh) 2011-08-10
CN102150156B true CN102150156B (zh) 2015-06-10

Family

ID=41465058

Family Applications (1)

Application Number Title Priority Date Filing Date
CN200980133134.8A Expired - Fee Related CN102150156B (zh) 2008-07-03 2009-07-02 优化用于机器翻译的参数

Country Status (6)

Country Link
US (2) US8744834B2 (ko)
EP (1) EP2318953A4 (ko)
JP (1) JP5572624B2 (ko)
KR (1) KR101623891B1 (ko)
CN (1) CN102150156B (ko)
WO (1) WO2010003117A2 (ko)

Families Citing this family (40)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8097081B2 (en) * 2008-06-05 2012-01-17 Soraa, Inc. High pressure apparatus and method for nitride crystal growth
US8744834B2 (en) * 2008-07-03 2014-06-03 Google Inc. Optimizing parameters for machine translation
US9176952B2 (en) * 2008-09-25 2015-11-03 Microsoft Technology Licensing, Llc Computerized statistical machine translation with phrasal decoder
WO2010046782A2 (en) 2008-10-24 2010-04-29 App Tek Hybrid machine translation
US8843359B2 (en) * 2009-02-27 2014-09-23 Andrew Nelthropp Lauder Language translation employing a combination of machine and human translations
US8285536B1 (en) 2009-07-31 2012-10-09 Google Inc. Optimizing parameters for machine translation
US8265923B2 (en) * 2010-05-11 2012-09-11 Xerox Corporation Statistical machine translation employing efficient parameter training
JP5650440B2 (ja) * 2010-05-21 2015-01-07 日本電信電話株式会社 素性重み学習装置、Ｎ−ｂｅｓｔスコアリング装置、Ｎ−ｂｅｓｔリランキング装置、それらの方法およびプログラム
US9201871B2 (en) 2010-06-11 2015-12-01 Microsoft Technology Licensing, Llc Joint optimization for machine translation system combination
US8326600B2 (en) * 2010-08-11 2012-12-04 Google Inc. Evaluating and modifying transliteration rules
KR101735438B1 (ko) * 2010-10-18 2017-05-15 한국전자통신연구원 실시간 번역 지식 자동 추출/검증 방법 및 그 장치
US8660836B2 (en) 2011-03-28 2014-02-25 International Business Machines Corporation Optimization of natural language processing system based on conditional output quality at risk
US8798984B2 (en) * 2011-04-27 2014-08-05 Xerox Corporation Method and system for confidence-weighted learning of factored discriminative language models
JP5548176B2 (ja) * 2011-09-16 2014-07-16 日本電信電話株式会社 翻訳最適化装置、方法、及びプログラム
JP5694893B2 (ja) * 2011-10-20 2015-04-01 日本電信電話株式会社 最適翻訳文選択装置、翻訳文選択モデル学習装置、方法、及びプログラム
US9323746B2 (en) * 2011-12-06 2016-04-26 At&T Intellectual Property I, L.P. System and method for collaborative language translation
US8874428B2 (en) * 2012-03-05 2014-10-28 International Business Machines Corporation Method and apparatus for fast translation memory search
US20140046651A1 (en) * 2012-08-13 2014-02-13 Xerox Corporation Solution for max-string problem and translation and transcription systems using same
JP5985344B2 (ja) * 2012-10-10 2016-09-06 日本電信電話株式会社 システムパラメータ最適化装置、方法、及びプログラム
CN103020002B (zh) * 2012-11-27 2015-11-18 中国人民解放军信息工程大学 可重构多处理器系统
US9195644B2 (en) 2012-12-18 2015-11-24 Lenovo Enterprise Solutions (Singapore) Pte. Ltd. Short phrase language identification
JP5889225B2 (ja) * 2013-01-31 2016-03-22 日本電信電話株式会社 近似オラクル文選択装置、方法、及びプログラム
JP6315980B2 (ja) * 2013-12-24 2018-04-25 株式会社東芝 デコーダ、デコード方法およびプログラム
US9653071B2 (en) * 2014-02-08 2017-05-16 Honda Motor Co., Ltd. Method and system for the correction-centric detection of critical speech recognition errors in spoken short messages
US9940658B2 (en) 2014-02-28 2018-04-10 Paypal, Inc. Cross border transaction machine translation
US9881006B2 (en) 2014-02-28 2018-01-30 Paypal, Inc. Methods for automatic generation of parallel corpora
US9530161B2 (en) 2014-02-28 2016-12-27 Ebay Inc. Automatic extraction of multilingual dictionary items from non-parallel, multilingual, semi-structured data
US9569526B2 (en) 2014-02-28 2017-02-14 Ebay Inc. Automatic machine translation using user feedback
US20170024659A1 (en) * 2014-03-26 2017-01-26 Bae Systems Information And Electronic Systems Integration Inc. Method for data searching by learning and generalizing relational concepts from a few positive examples
US9530404B2 (en) * 2014-10-06 2016-12-27 Intel Corporation System and method of automatic speech recognition using on-the-fly word lattice generation with word histories
JP6620934B2 (ja) * 2016-01-29 2019-12-18 パナソニックＩｐマネジメント株式会社 翻訳支援方法、翻訳支援装置、翻訳装置及び翻訳支援プログラム
KR102565275B1 (ko) 2016-08-10 2023-08-09 삼성전자주식회사 병렬 처리에 기초한 번역 방법 및 장치
CN107798386B (zh) * 2016-09-01 2022-02-15 微软技术许可有限责任公司 基于未标注数据的多过程协同训练
KR101719107B1 (ko) * 2016-10-27 2017-04-06 박성국 번역을 위한 서버 및 번역 방법
US10055400B2 (en) 2016-11-11 2018-08-21 International Business Machines Corporation Multilingual analogy detection and resolution
US10061770B2 (en) 2016-11-11 2018-08-28 International Business Machines Corporation Multilingual idiomatic phrase translation
KR102458244B1 (ko) 2017-11-23 2022-10-24 삼성전자주식회사 기계 번역 방법 및 장치
CN109118113B (zh) * 2018-08-31 2021-08-10 传神语联网网络科技股份有限公司 Etm架构及词移距离
US11341340B2 (en) * 2019-10-01 2022-05-24 Google Llc Neural machine translation adaptation
CN114881008A (zh) * 2022-04-24 2022-08-09 北京有竹居网络技术有限公司 一种文本生成方法、装置、电子设备及介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1573739A (zh) * 2003-06-04 2005-02-02 株式会社国际电气通信基础技术研究所 用于改良机器翻译之翻译知识的方法和装置
CN1855090A (zh) * 2005-04-26 2006-11-01 株式会社东芝 用于将日文翻译成中文的装置和方法
CN101158947A (zh) * 2006-09-22 2008-04-09 株式会社东芝 机器翻译的方法和装置

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2126380C (en) * 1993-07-22 1998-07-07 Wu Chou Minimum error rate training of combined string models
JPH07334368A (ja) * 1994-06-08 1995-12-22 Hitachi Ltd 知識ベースシステムおよび認識システム
US8874431B2 (en) * 2001-03-16 2014-10-28 Meaningful Machines Llc Knowledge system method and apparatus
US20030110023A1 (en) * 2001-12-07 2003-06-12 Srinivas Bangalore Systems and methods for translating languages
US7571098B1 (en) 2003-05-29 2009-08-04 At&T Intellectual Property Ii, L.P. System and method of spoken language understanding using word confusion networks
JP2006053683A (ja) * 2004-08-10 2006-02-23 Advanced Telecommunication Research Institute International 音声認識および機械翻訳装置
JP4084789B2 (ja) * 2004-09-28 2008-04-30 株式会社国際電気通信基礎技術研究所 統計機械翻訳装置および統計機械翻訳プログラム
US7536295B2 (en) * 2005-12-22 2009-05-19 Xerox Corporation Machine translation using non-contiguous fragments of text
US7848917B2 (en) 2006-03-30 2010-12-07 Microsoft Corporation Common word graph based multimodal input
US8209163B2 (en) 2006-06-02 2012-06-26 Microsoft Corporation Grammatical element generation in machine translation
US7856351B2 (en) 2007-01-19 2010-12-21 Microsoft Corporation Integrated speech recognition and semantic classification
US8744834B2 (en) 2008-07-03 2014-06-03 Google Inc. Optimizing parameters for machine translation

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1573739A (zh) * 2003-06-04 2005-02-02 株式会社国际电气通信基础技术研究所 用于改良机器翻译之翻译知识的方法和装置
CN1855090A (zh) * 2005-04-26 2006-11-01 株式会社东芝 用于将日文翻译成中文的装置和方法
CN101158947A (zh) * 2006-09-22 2008-04-09 株式会社东芝 机器翻译的方法和装置

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Lattice Minimum Bayes-Risk Decoding for Statistical Machine Translation;RoyW. Tromble 等;《Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing》;20081031;第620-629页 *
Lattice-based Minimum Error Rate Training for Statistical Machine Translation;Wolfgang Macherey 等;《Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing》;20081031;第725-734页 *
Minimum Bayes-Risk Decoding for Statistical Machine Translation;Shankar Kumar等;《In Proc.HLT-NAACL》;20041231;第169-176页 *

Also Published As

Publication number Publication date
EP2318953A4 (en) 2013-10-30
KR20110043645A (ko) 2011-04-27
US20100004920A1 (en) 2010-01-07
JP2011527471A (ja) 2011-10-27
WO2010003117A2 (en) 2010-01-07
CN102150156A (zh) 2011-08-10
KR101623891B1 (ko) 2016-05-24
US8744834B2 (en) 2014-06-03
JP5572624B2 (ja) 2014-08-13
WO2010003117A3 (en) 2010-11-18
US20100004919A1 (en) 2010-01-07
WO2010003117A8 (en) 2010-03-11
EP2318953A2 (en) 2011-05-11

Similar Documents

Publication Publication Date Title
CN102150156B (zh) 优化用于机器翻译的参数
US11468233B2 (en) Intention identification method, intention identification apparatus, and computer-readable recording medium
US8401836B1 (en) Optimizing parameters for machine translation
CN103430232B (zh) 利用设备停靠情境的语音识别
US7035788B1 (en) Language model sharing
AU2017408800B2 (en) Method and system of mining information, electronic device and readable storable medium
US20210232948A1 (en) Question responding apparatus, question responding method and program
WO2020244065A1 (zh) 基于人工智能的字向量定义方法、装置、设备及存储介质
US20210216887A1 (en) Knowledge graph alignment with entity expansion policy network
CN105340004A (zh) 用于发音学习的计算机实现的方法、计算机可读介质和系统
JP2021152963A (ja) 語義特徴の生成方法、モデルトレーニング方法、装置、機器、媒体及びプログラム
CN110569505B (zh) 一种文本输入方法及装置
CN110352423B (zh) 使用噪声信道模型生成目标序列的方法、存储介质和系统
CN111274822A (zh) 语义匹配方法、装置、设备及存储介质
CN110874536A (zh) 语料质量评估模型生成方法和双语句对互译质量评估方法
WO2014073206A1 (ja) 情報処理装置、及び、情報処理方法
US11681880B2 (en) Auto transformation of network data models using neural machine translation
CN111753029A (zh) 实体关系抽取方法、装置
CN105229625A (zh) 获取有效hmm的混合散列方案
CN111814493A (zh) 机器翻译方法、装置、电子设备和存储介质
US11562123B2 (en) Method and apparatus for fusing position information, and non-transitory computer-readable recording medium
US11481547B2 (en) Framework for chinese text error identification and correction
CN112084784A (zh) 预测语义角色标注的功能性标记
CN112487813A (zh) 命名实体识别方法及系统、电子设备及存储介质
CN116069947A (zh) 一种日志数据事件图谱构建方法、装置、设备及存储介质

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20150610

Termination date: 20180702

CF01 Termination of patent right due to non-payment of annual fee